包含提供增强的软组织对比度的磁共振(MR)成像设备的直线加速器(直线加速器)特别适合于腹部放射治疗。特别是,治疗计划所需的腹部肿瘤和危险器官(OAR)的准确分割成为可能。目前,这种分割是由放射肿瘤学家手动执行的.这个过程是非常耗时的,并且受到操作者之间和内部的变化的影响。在这项工作中,基于深度学习的自动分割解决方案在0.35TMR图像上研究了腹部OAR。
■收集了121组腹部MR图像及其相应的地面实况分割并用于这项工作。感兴趣的OAR包括肝脏,肾脏,脊髓,胃和十二指肠.已经在2D中训练了几个基于UNet的模型(经典UNet,ResattentionUNet,EfficientNetUNet,和nnUNet)。然后用3D策略训练最佳模型,以研究可能的改进。几何指标,如骰子相似系数(DSC),交汇处(IoU),进行Hausdorff距离(HD)和计算体积的分析(归功于Bland-Altman图)以评估结果。
■在3D模式下训练的nnUNet实现了最佳性能,肝脏的DSC评分,肾脏,脊髓,胃,十二指肠分别为0.96±0.01、0.91±0.02、0.91±0.01、0.83±0.10和0.69±0.15。匹配的IoU评分分别为0.92±0.01、0.84±0.04、0.84±0.02、0.54±0.16和0.72±0.13。相应的HD评分为13.0±6.0mm,16.0±6.6mm,3.3±0.7mm,35.0±33.0mm,和42.0±24.0毫米。计算体积的分析遵循相同的行为。
■尽管十二指肠的分割结果不是最佳的,这些发现暗示了3DnnUNet模型对于0.35TMR-Linac图像的腹部OAR分割的潜在临床应用.
UNASSIGNED: Linear accelerator (linac) incorporating a magnetic resonance (MR) imaging device providing enhanced soft tissue contrast is particularly suited for abdominal radiation therapy. In particular, accurate segmentation for abdominal tumors and organs at risk (OARs) required for the treatment planning is becoming possible. Currently, this segmentation is performed manually by radiation oncologists. This process is very time consuming and subject to inter and intra operator variabilities. In this work, deep learning based automatic segmentation solutions were investigated for abdominal OARs on 0.35 T MR-images.
UNASSIGNED: One hundred and twenty one sets of abdominal MR images and their corresponding ground truth segmentations were collected and used for this work. The OARs of interest included the liver, the kidneys, the spinal cord, the stomach and the duodenum. Several UNet based models have been trained in 2D (the Classical UNet, the ResAttention UNet, the EfficientNet UNet, and the
nnUNet). The best model was then trained with a 3D strategy in order to investigate possible improvements. Geometrical metrics such as Dice Similarity Coefficient (DSC), Intersection over Union (IoU), Hausdorff Distance (HD) and analysis of the calculated volumes (thanks to Bland-Altman plot) were performed to evaluate the results.
UNASSIGNED: The
nnUNet trained in 3D mode achieved the best performance, with DSC scores for the liver, the kidneys, the spinal cord, the stomach, and the duodenum of 0.96 ± 0.01, 0.91 ± 0.02, 0.91 ± 0.01, 0.83 ± 0.10, and 0.69 ± 0.15, respectively. The matching IoU scores were 0.92 ± 0.01, 0.84 ± 0.04, 0.84 ± 0.02, 0.54 ± 0.16 and 0.72 ± 0.13. The corresponding HD scores were 13.0 ± 6.0 mm, 16.0 ± 6.6 mm, 3.3 ± 0.7 mm, 35.0 ± 33.0 mm, and 42.0 ± 24.0 mm. The analysis of the calculated volumes followed the same behavior.
UNASSIGNED: Although the segmentation results for the duodenum were not optimal, these findings imply a potential clinical application of the 3D
nnUNet model for the segmentation of abdominal OARs for images from 0.35 T MR-Linac.